The MCP directory / Open to explore
MCP server directory.
Find your next tool.
Search 3,974 indexed servers from the official MCP Registry and selected vendor documentation. Find remote endpoints and local packages, inspect the publisher’s setup details, then connect in your AI client.
Where will your next task take you?
Free discovery · no account · no API key
Let your agent do the finding.
Read https://toolcargo.com/agents.txt, then find the MCP servers I need and help me connect them. Ask me what I want to do first.Or add https://toolcargo.com/mcp as a Streamable HTTP MCP server. Discovery is free and needs no account.
Compare task fit, publisher, permissions and a small acceptance test with the MCP server selection guide.
Connect directly to official MCP servers
Vendor setup guides for your existing accounts. These connections run with the vendor; ToolCargo does not host them or supply their credentials.
Browse the remote MCP server directory →
Not sure which connection to choose? Read local vs remote MCP servers. Building a discovery workflow? See the MCP server search API reference.
Parallel Browser MCP
Close detailsMCP server for parallel browser automation across multiple providers.
Directory identity: io.github.etairl/parallel-browser-mcp · Version: 0.1.14
{
"remotes": [],
"packages": [
{
"registryType": "npm",
"registryBaseUrl": "https://registry.npmjs.org",
"identifier": "parallel-browser-mcp",
"version": "0.1.14",
"runtimeHint": "npx",
"transport": {
"type": "stdio"
},
"environmentVariables": [
{
"description": "Inline JSON configuration for providers and defaults. See README for shape.",
"name": "BROWSER_MCP_CONFIG"
},
{
"description": "Path to a JSON file with provider configuration.",
"name": "BROWSER_MCP_CONFIG_PATH"
},
{
"description": "Browserbase API key (required when using the browserbase provider).",
"isSecret": true,
"name": "BROWSERBASE_API_KEY"
},
{
"description": "Browserbase project ID (required when using the browserbase provider, unless set in config).",
"name": "BROWSERBASE_PROJECT_ID"
},
{
"description": "Anchor Browser API key (required when using the anchor provider).",
"isSecret": true,
"name": "ANCHOR_API_KEY"
},
{
"description": "Cloudflare API token (required when using the cloudflare provider).",
"isSecret": true,
"name": "CLOUDFLARE_API_TOKEN"
},
{
"description": "Cloudflare account ID (required when using the cloudflare provider).",
"name": "CLOUDFLARE_ACCOUNT_ID"
},
{
"description": "Set to 'true' to launch the local Playwright provider via CloakBrowser (https://cloakbrowser.dev/) stealth Chromium. Requires installing the optional 'cloakbrowser' npm package.",
"name": "PLAYWRIGHT_USE_CLOAKBROWSER"
}
]
}
]
}Remote URLs go into your client's MCP settings. Local packages need a compatible runtime. Check required headers, environment variables, permissions and provider costs before setup.
Publisher repository ↗3,974 results
Index updated 2026-10-02
- Local packageThird-party
Google Docs
io.github.domdomegg/google-documents-mcp
Allow AI systems to read and edit Google Docs.
View connection details → - Local packageThird-party
Google Drive
io.github.domdomegg/google-drive-mcp
Allow AI systems to list, search, upload, download, and manage files and folders in Google Drive.
View connection details → - Local packageThird-party
Google Maps Places
io.github.domdomegg/google-maps-places-mcp
Allow AI systems to search for places and get business info via Google Maps Places API.
View connection details → - Local packageThird-party
Google Sheets
io.github.domdomegg/google-sheets-mcp
Allow AI systems to read, write, and query spreadsheet data via Google Sheets.
View connection details → - Local packageThird-party
pmll-memory-mcp
io.github.drQedwards/pmll-memory-mcp
PMLL Memory MCP — persistent KV context memory and Q-promise deduplication.
View connection details → - Local packageThird-party
Google data (Trends, YouTube, Ads Transparency, Play)
io.github.ducnhd/google-data-mcp
Google Trends, YouTube, Ads Transparency and Play reviews over plain HTTP. No API key.
View connection details → - Local packageThird-party
Google Tasks MCP Server
io.github.ebmurha/google-tasks-mcp
Manage Google Tasks from MCP-compatible AI clients.
View connection details → - Local packageThird-party
Postgres MCP
io.github.edelciomolina/postgres-mcp
PostgreSQL MCP wrapper with .env credential mapping, tool selection, and safe read-only defaults.
View connection details → - Local packageThird-party
Memory Fabric
io.github.elViRafa/memory-fabric
File-first, local-first MCP memory for AI coding assistants: Markdown + YAML, no vector DB.
View connection details → - Local packageThird-party
PostgreSQL (hardened, read-only)
io.github.Eszetael/postgres-mcp-hardened
Read-only PostgreSQL over MCP. Writes refused at the parsed SQL, plus a READ ONLY transaction.
View connection details → - Local packageThird-party
Parallel Browser MCP
io.github.etairl/parallel-browser-mcp
MCP server for parallel browser automation across multiple providers.
View connection details → - Remote URLThird-party
AWS Builder
io.github.Evozim/aws-builder
AWS CloudFormation and Terraform infrastructure blueprint builder.
View connection details → - Remote URLThird-party
Execute aws-builder-mcp
io.github.Evozim/aws-builder-mcp
Premium agentic endpoint for aws-builder-mcp.
View connection details → - Remote URLThird-party
Execute aws-key-revoker-webhook-mcp
io.github.Evozim/aws-key-revoker-webhook-mcp
Premium agentic endpoint for aws-key-revoker-webhook-mcp.
View connection details → - Remote URLThird-party
Execute baidu-china-search-mcp
io.github.Evozim/baidu-china-search-mcp
Premium agentic endpoint for baidu-china-search-mcp.
View connection details → - Remote URLThird-party
Execute chroot-filesystem-jail-mcp
io.github.Evozim/chroot-filesystem-jail-mcp
Premium agentic endpoint for chroot-filesystem-jail-mcp.
View connection details → - Remote URLThird-party
Execute cloudflare-turnstile-bypass-mcp
io.github.Evozim/cloudflare-turnstile-bypass-mcp
Premium agentic endpoint for cloudflare-turnstile-bypass-mcp.
View connection details → - Remote URLThird-party
Execute dockerfile-credential-mcp
io.github.Evozim/dockerfile-credential-mcp
Premium agentic endpoint for dockerfile-credential-mcp.
View connection details → - Remote URLThird-party
Execute duckduckgo-privacy-search-mcp
io.github.Evozim/duckduckgo-privacy-search-mcp
Premium agentic endpoint for duckduckgo-privacy-search-mcp.
View connection details → - Remote URLThird-party
Linear-Task-Broker
io.github.Evozim/linear-broker
Integrates agents with Linear software development workflows.
View connection details → - Local packageThird-party
vanguard-memory-node
io.github.ezumba/vanguard-memory-node
Local deterministic BM25 memory for AI agents. Offline-first, no API key, SHA-256 shards, stdio.
View connection details → - Local packageThird-party
Nuzo Memory
io.github.fabionfsc/nuzo-memory
Local-first, auditable memory for MCP-compatible AI agents with explicit writes and SQLite storage.
View connection details → - Local packageThird-party
e2e-runner
io.github.fastslack/e2e-runner
JSON-driven E2E test runner with parallel Chrome pool execution and 16 MCP tools.
View connection details → - Local packageThird-party
invisible_playwright_mcp
io.github.feder-cr/invisible-playwright-mcp
AI browser agent: browses, clicks, types, and reads real web pages from plain-English instructions.
View connection details →
This directory combines dated registry listings and selected vendor-documentation entries. Documentation checks are not live account or client verification. Third-party servers run with their own providers, credentials and pricing. ToolCargo discovery supplies setup metadata; it does not run their tools. Explore ToolCargo's hosted connectors.